{"id":"https://openalex.org/W4225265678","doi":"https://doi.org/10.1145/3523111.3523127","title":"Mean-variance Based Risk-sensitive Reinforcement Learning with Interpretable Attention","display_name":"Mean-variance Based Risk-sensitive Reinforcement Learning with Interpretable Attention","publication_year":2022,"publication_date":"2022-02-18","ids":{"openalex":"https://openalex.org/W4225265678","doi":"https://doi.org/10.1145/3523111.3523127"},"language":"en","primary_location":{"id":"doi:10.1145/3523111.3523127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523111.3523127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 the 5th International Conference on Machine Vision and Applications (ICMVA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109456089","display_name":"Woo Kyung Kim","orcid":"https://orcid.org/0000-0002-0974-903X"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woo Kyung Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Sungkyunkwan University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sungkyunkwan University, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701668","display_name":"Youngseok Lee","orcid":"https://orcid.org/0000-0002-3015-5922"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngseok Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Sungkyunkwan University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Sungkyunkwan University, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001227049","display_name":"Honguk Woo","orcid":"https://orcid.org/0000-0001-6948-3440"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Honguk Woo","raw_affiliation_strings":["Department of Computer Science and Engineering, Sungkyunkwan University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sungkyunkwan University, South Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":0.2775,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6116286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9917102456092834},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8047029972076416},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6816104650497437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6433829069137573},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6246799826622009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6215294599533081},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5743950009346008},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.47588932514190674},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.43614447116851807},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4149831235408783},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41178175806999207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.153334379196167},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.061747074127197266}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9917102456092834},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8047029972076416},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6816104650497437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6433829069137573},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6246799826622009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6215294599533081},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5743950009346008},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.47588932514190674},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.43614447116851807},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4149831235408783},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41178175806999207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.153334379196167},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.061747074127197266},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3523111.3523127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523111.3523127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 the 5th International Conference on Machine Vision and Applications (ICMVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W134786152","https://openalex.org/W2783967294","https://openalex.org/W2970857152","https://openalex.org/W2996195849","https://openalex.org/W2998004401","https://openalex.org/W3012550998","https://openalex.org/W3206010851","https://openalex.org/W4288079541"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W2806259446","https://openalex.org/W2963326959","https://openalex.org/W4247136043","https://openalex.org/W4312407344","https://openalex.org/W4384115502","https://openalex.org/W4226258012","https://openalex.org/W4383681494"],"abstract_inverted_index":{"Risk-sensitive":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"has":[4],"been":[5],"studied":[6],"to":[7,88],"address":[8],"the":[9,21,35,58,67,84],"risk":[10],"and":[11],"uncertainty":[12],"in":[13,34,52],"autonomous":[14],"systems.":[15],"While":[16],"a":[17,54],"comprehensive":[18],"understanding":[19],"for":[20],"behaviors":[22],"of":[23,37,62,69],"RL":[24],"agents":[25],"plays":[26],"an":[27,45,63],"important":[28],"role,":[29],"interpretability":[30,85],"was":[31],"rarely":[32],"discussed":[33],"context":[36],"risk-sensitivity":[38],"RL.":[39,73],"In":[40],"this":[41],"paper,":[42],"we":[43,78],"present":[44],"interpretable":[46],"visualization":[47],"scheme":[48,82],"with":[49,86],"attention":[50],"mechanism":[51],"which":[53],"saliency":[55],"map":[56],"represents":[57],"relative":[59],"influence":[60],"degree":[61],"input":[64],"state":[65],"on":[66],"decision-making":[68],"mean-variance":[70],"based":[71],"risk-sensitive":[72,89],"Through":[74],"2D":[75],"navigation":[76],"experiments,":[77],"demonstrate":[79],"that":[80],"our":[81],"provides":[83],"regard":[87],"levels.":[90]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}